Related papers: A Pre-trained Reaction Embedding Descriptor Captur…

Inspired by the recent success of sequence modeling in RL and the use of masked language model for pre-training, we propose a masked model for pre-training in RL, RePreM (Representation Pre-training with Masked Model), which trains the…

The ability to generate and recognize sequential data is fundamental for autonomous systems operating in dynamic environments. Inspired by the key principles of the brain-predictive coding and the Bayesian brain-we propose a novel…

Recurrent neural networks (RNNs) have shown the ability to improve scene parsing through capturing long-range dependencies among image units. In this paper, we propose dense RNNs for scene labeling by exploring various long-range semantic…

Action recognition is a vital task in computer vision, and many methods are developed to push it to the limit. However, current action recognition models have huge computational costs, which cannot be deployed to real-world tasks on mobile…

Reaction and retrosynthesis prediction are fundamental tasks in computational chemistry that have recently garnered attention from both the machine learning and drug discovery communities. Various deep learning approaches have been proposed…

Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the…

The quadratic complexity of dot-product attention introduced in Transformer remains a fundamental bottleneck impeding the progress of foundation models toward unbounded context lengths. Addressing this challenge, we introduce the Deep…

Less than 1% of protein sequences are structurally and functionally annotated. Natural Language Processing (NLP) community has recently embraced self-supervised learning as a powerful approach to learn representations from unlabeled text,…

DNA-binding proteins (DBPs) are integral to gene regulation and cellular processes, making their accurate identification essential for understanding biological functions and disease mechanisms. Experimental methods for DBP identification…

Modeling of turbulent combustion system requires modeling the underlying chemistry and the turbulent flow. Solving both systems simultaneously is computationally prohibitive. Instead, given the difference in scales at which the two…

Online Action Detection (OAD) detects actions in streaming videos using past observations. State-of-the-art OAD approaches model past observations and their interactions with an anticipated future. The past is encoded using short- and…

Machine learning models that predict the feasibility of chemical reactions have become central to automated synthesis planning. Despite their predictive success, these models often lack transparency and interpretability. We introduce a…

A deep neural network (DNN) model consisting of two hidden layers was proposed for predicting the immediate environments of specific atoms based on X-ray absorption near-edge spectra (XANES). The output layer of the DNN can be adjusted to…

While deep learning, particularly convolutional neural networks (CNNs), has revolutionized remote sensing (RS) change detection (CD), existing approaches often miss crucial features due to neglecting global context and incomplete change…

Although RDBs store vast amounts of rich, informative data spread across interconnected tables, the progress of predictive machine learning models as applied to such tasks arguably falls well behind advances in other domains such as…

Deep convolutional neural networks have been shown to successfully recognize facial emotions for the past years in the realm of computer vision. However, the existing detection approaches are not always reliable or explainable, we here…

Pattern recognition based on RGB-Event data is a newly arising research topic and previous works usually learn their features using CNN or Transformer. As we know, CNN captures the local features well and the cascaded self-attention…

Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified…

We present a novel interpretable machine learning model to accurately predict complex rippling deformations of Multi-Walled Carbon Nanotubes(MWCNTs) made of millions of atoms. Atomistic-physics-based models are accurate but computationally…

Micro-expression has emerged as a promising modality in affective computing due to its high objectivity in emotion detection. Despite the higher recognition accuracy provided by the deep learning models, there are still significant scope…